© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2915
    Prev
    Next
    INDEX
    Explanations

    certainly or definitely followed by a verb/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ટ
    1.89
    س
    1.86
     wynosi
    1.56
    𝘴
    1.53
    еты
    1.47
    িত্য
    1.45
     İli
    1.45
     Той
    1.44
    rast
    1.43
     concep
    1.42
    POSITIVE LOGITS
    तमंद
    2.11
     chắn
    1.86
    પણે
    1.82
    вача
    1.75
    无疑
    1.61
    卩
    1.53
     rectifier
    1.53
     heinous
    1.50
     कप्तान
    1.49
     hypersurfaces
    1.49
    Activations Density 0.040%

    No Known Activations